Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4347 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.9041. Min Act: -0.0000

Data Index: 929714 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.8208. Min Act: -0.0000

Data Index: 300324 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.7660. Min Act: -0.0000

Data Index: 871732 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.8377. Min Act: -0.0000

Data Index: 78900 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.7461. Min Act: -0.0000

Data Index: 455862 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.6074. Min Act: -0.0000

Data Index: 1298564 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.5955. Min Act: -0.0000

Data Index: 632365 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.5390. Min Act: -0.0000

Data Index: 1159737 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1205948 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1050718 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.3132. Min Act: -0.0000

Data Index: 281367 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1903. Min Act: -0.0000

Data Index: 213276 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.2525. Min Act: -0.0000

Data Index: 948660 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1991. Min Act: -0.0000

Data Index: 1027087 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1725. Min Act: -0.0000

Data Index: 1102571 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.2089. Min Act: -0.0000

Data Index: 617945 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1761. Min Act: -0.0000

Data Index: 944227 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1023615 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.1148. Min Act: -0.0000

Data Index: 500764 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.9041. Min Range: -1.9041

Max Act: 1.0782. Min Act: -0.0000

Data Index: 701099 (C4 (Web Text))

Max Activating Token Index: 569